Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    hello world and main window

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ł
    1.02
     CHAR
    1.01
     vardır
    0.98
     Fish
    0.97
     agli
    0.94
     αυ
    0.93
     καλ
    0.93
     gl
    0.93
     ת
    0.92
     Lys
    0.91
    POSITIVE LOGITS
    ()
    1.43
    ()[
    1.43
    ()`
    1.41
    ()+"
    1.37
    ().
    1.25
    ())
    1.25
    ()+
    1.23
    ()->
    1.22
    __()
    1.22
    ขณะ
    1.22
    Act Density 0.055%

    No Known Activations